INDEX

Explanations

web content

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Automatic

-0.28

 Automatically

-0.28

 automatic

-0.27

_deep

-0.27

 paran

-0.27

 mÃº

-0.26

automatic

-0.26

dec

-0.26

 capacity

-0.25

dec

-0.25

POSITIVE LOGITS

åĪĩæĸŃ

0.28

@mail

0.26

ByEmail

0.26

.addEdge

0.26

ç½ĳç»ľä¼łæĴŃ

0.25

ucer

0.25

 Hyde

0.24

 trÃ¹ng

0.24

åŃĹç¬¬

0.24

allows

0.24

Activations Density 0.021%

web content

No Comments

No Known Activations